Anomaly detection deals with detecting deviations from established patterns within data. It has various applications like autonomous driving, predictive maintenance, and medical diagnosis. To improve anomaly detection accuracy, transfer learning can be applied to large, pre-trained models and adapt them to the specific application context. In this paper, we propose a novel framework for online-adaptive anomaly detection using transfer learning. The approach adapts to different environments by selecting visually similar training images and online fitting a normality model to EfficientNet features extracted from the training subset. Anomaly detection is then performed by computing the Mahalanobis distance between the normality model and the test image features. Different similarity measures (SIFT/FLANN, Cosine) and normality models (MVG, OCSVM) are employed and compared with each other. We evaluate the approach on different anomaly detection benchmarks and data collected in controlled laboratory settings. Experimental results showcase a detection accuracy exceeding 0.975, outperforming the state-of-the-art ET-NET approach.

翻译：异常检测旨在识别数据中偏离既定模式的现象，其在自动驾驶、预测性维护及医疗诊断等领域具有广泛应用。为提高异常检测精度，可将迁移学习应用于大规模预训练模型，使其适应特定应用场景。本文提出一种基于迁移学习的在线自适应异常检测新框架。该方法通过选取视觉相似的训练图像，并对训练子集提取的EfficientNet特征在线拟合正态性模型，从而适应不同环境。异常检测通过计算正态性模型与测试图像特征之间的马氏距离实现。研究采用多种相似性度量方法（SIFT/FLANN、余弦相似度）与正态性模型（多元高斯分布、单类支持向量机）进行对比验证。我们在多个异常检测基准数据集及受控实验室环境采集数据上评估该方法，实验结果显示其检测精度超过0.975，性能优于当前最先进的ET-NET方法。